figma_skill · Figma Unified MCP: Risk & Policy

WHAT IT DOES

What figma_skill does on Figma Unified

AI agents invoke figma_skill to trigger actions in Figma Unified. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why figma_skill needs a policy

figma_skill triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

figma_skill Rate-limited

figma_skill stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "figma_skill": {
      "limits": [
        {
          "counter": "figma_skill_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Figma Unified, so you can run agents against it safely.

FAQ

Questions about figma_skill

What does the figma_skill tool do? +

Invoke a pre-built design workflow (skill/prompt). Returns step-by-step instructions that you MUST follow using the available Figma tools.\n\nAvailable skills:\n${catalogList}. It is categorised as a Execute tool in the Figma Unified MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on figma_skill? +

Register the Figma Unified MCP server in PolicyLayer and add a rule for figma_skill: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Figma Unified. Nothing to install.

What risk level is figma_skill? +

figma_skill is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit figma_skill? +

Yes. Add a rate_limit block to the figma_skill rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block figma_skill completely? +

Set action: deny in the PolicyLayer policy for figma_skill. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides figma_skill? +

figma_skill is provided by the Figma Unified MCP server (sso-ss/figma-unified-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.